Spaces:
Running
Running
Upload folder using huggingface_hub
Browse files- app/pages.py +26 -36
app/pages.py
CHANGED
|
@@ -173,23 +173,21 @@ def general_reasoning():
|
|
| 173 |
'ZBench': 'zbench',
|
| 174 |
'IndoMMLU': 'indommlu'}
|
| 175 |
|
| 176 |
-
left, center, _, right = st.columns([0.2, 0.2, 0.
|
| 177 |
with left:
|
| 178 |
category_one = st.selectbox('Zero or Few Shot', filters_levelone)
|
| 179 |
with center:
|
| 180 |
category_two = st.selectbox('Dataset', filters_leveltwo)
|
| 181 |
-
|
| 182 |
-
|
| 183 |
-
# sortby = st.selectbox('sorted by', ['Ascending', 'Descending'])
|
| 184 |
|
| 185 |
sortby = 'Ascending'
|
| 186 |
|
| 187 |
if category_one or category_two or sortby:
|
| 188 |
category_one = category_one_dict[category_one]
|
| 189 |
category_two = category_two_dict[category_two]
|
| 190 |
-
draw('general_reasoning', category_one, category_two, 'Accuracy',sortby)
|
| 191 |
-
|
| 192 |
-
# draw_only_acc('general_reasoning', 'zero_shot', 'MMLU Full', 'Descending')
|
| 193 |
|
| 194 |
def flores():
|
| 195 |
st.title("Task: FLORES-Translation")
|
|
@@ -209,22 +207,21 @@ def flores():
|
|
| 209 |
'Malay to English': 'zsm2eng'}
|
| 210 |
|
| 211 |
|
| 212 |
-
left, center, _, right = st.columns([0.2, 0.2, 0.
|
| 213 |
with left:
|
| 214 |
category_one = st.selectbox('Zero or Few Shot', filters_levelone)
|
| 215 |
with center:
|
| 216 |
category_two = st.selectbox('Dataset', filters_leveltwo)
|
| 217 |
-
|
| 218 |
-
|
| 219 |
|
| 220 |
sortby = 'Ascending'
|
| 221 |
|
| 222 |
if category_one or category_two or sortby:
|
| 223 |
category_one = category_one_dict[category_one]
|
| 224 |
category_two = category_two_dict[category_two]
|
| 225 |
-
draw('flores_translation', category_one, category_two, 'BLEU',sortby)
|
| 226 |
-
|
| 227 |
-
# draw_flores_translation('zero_shot', 'Indonesian to English', 'Descending')
|
| 228 |
|
| 229 |
def emotion():
|
| 230 |
st.title("Task: Emotion")
|
|
@@ -240,23 +237,21 @@ def emotion():
|
|
| 240 |
category_two_dict = {'Indonesian Emotion Classification': 'ind_emotion',
|
| 241 |
'SST2': 'sst2'}
|
| 242 |
|
| 243 |
-
left, center, _, right = st.columns([0.2, 0.2, 0.
|
| 244 |
with left:
|
| 245 |
category_one = st.selectbox('Zero or Few Shot', filters_levelone)
|
| 246 |
with center:
|
| 247 |
category_two = st.selectbox('Dataset', filters_leveltwo)
|
| 248 |
-
|
| 249 |
-
|
| 250 |
-
|
| 251 |
sortby = 'Ascending'
|
| 252 |
|
| 253 |
|
| 254 |
if category_one or category_two or sortby:
|
| 255 |
category_one = category_one_dict[category_one]
|
| 256 |
category_two = category_two_dict[category_two]
|
| 257 |
-
draw('emotion', category_one, category_two, 'Accuracy', sortby)
|
| 258 |
-
# else:
|
| 259 |
-
# draw_only_acc('emotion', 'zero_shot', 'Indonesian Emotion Classification', 'Descending')
|
| 260 |
|
| 261 |
def dialogue():
|
| 262 |
st.title("Task: Dialogue")
|
|
@@ -274,29 +269,27 @@ def dialogue():
|
|
| 274 |
'SAMSum': 'samsum',
|
| 275 |
'DialogSum': 'dialogsum'}
|
| 276 |
|
| 277 |
-
left, center, _,
|
| 278 |
with left:
|
| 279 |
category_one = st.selectbox('Zero or Few Shot', filters_levelone)
|
| 280 |
with center:
|
| 281 |
category_two = st.selectbox('Dataset', filters_leveltwo)
|
| 282 |
-
with
|
| 283 |
if category_two == 'DREAM':
|
| 284 |
sort = st.selectbox('Sort', ['Accuracy'])
|
| 285 |
else:
|
| 286 |
sort = st.selectbox('Sort', ['Average', 'ROUGE-1', 'ROUGE-2', 'ROUGE-L'])
|
| 287 |
-
|
| 288 |
-
#with right:
|
| 289 |
-
# sortby = st.selectbox('by', ['Ascending', 'Descending'])
|
| 290 |
|
|
|
|
|
|
|
|
|
|
| 291 |
sortby = 'Ascending'
|
| 292 |
|
| 293 |
-
|
| 294 |
if category_one or category_two or sort or sortby:
|
| 295 |
category_one = category_one_dict[category_one]
|
| 296 |
category_two = category_two_dict[category_two]
|
| 297 |
-
draw('dialogue', category_one, category_two, sort, sortby)
|
| 298 |
-
|
| 299 |
-
# draw_dialogue('zero_shot', 'DREAM', sort[0],'Descending')
|
| 300 |
|
| 301 |
def fundamental_nlp_tasks():
|
| 302 |
st.title("Task: Fundamental NLP Tasks")
|
|
@@ -316,20 +309,17 @@ def fundamental_nlp_tasks():
|
|
| 316 |
'RTE': 'rte',
|
| 317 |
'MRPC': 'mrpc'}
|
| 318 |
|
| 319 |
-
left, center, _, right = st.columns([0.2, 0.2, 0.
|
| 320 |
with left:
|
| 321 |
category_one = st.selectbox('Zero or Few Shot', filters_levelone)
|
| 322 |
with center:
|
| 323 |
category_two = st.selectbox('Dataset', filters_leveltwo)
|
| 324 |
-
|
| 325 |
-
|
| 326 |
-
# sortby = st.selectbox('sorted by', ['Ascending', 'Descending'])
|
| 327 |
|
| 328 |
sortby = 'Ascending'
|
| 329 |
|
| 330 |
if category_one or category_two or sortby:
|
| 331 |
category_one = category_one_dict[category_one]
|
| 332 |
category_two = category_two_dict[category_two]
|
| 333 |
-
draw('fundamental_nlp_tasks', category_one, category_two, 'Accuracy', sortby)
|
| 334 |
-
# else:
|
| 335 |
-
# draw_only_acc('fundamental_nlp_tasks', 'zero_shot', 'OCNLI', 'Descending')
|
|
|
|
| 173 |
'ZBench': 'zbench',
|
| 174 |
'IndoMMLU': 'indommlu'}
|
| 175 |
|
| 176 |
+
left, center, middle, _, right = st.columns([0.2, 0.2, 0.2, 0.2 ,0.2])
|
| 177 |
with left:
|
| 178 |
category_one = st.selectbox('Zero or Few Shot', filters_levelone)
|
| 179 |
with center:
|
| 180 |
category_two = st.selectbox('Dataset', filters_leveltwo)
|
| 181 |
+
with middle:
|
| 182 |
+
model_size_range = st.selectbox('Model Size', ['All', '<10B', '10B-30B', '>30B'])
|
|
|
|
| 183 |
|
| 184 |
sortby = 'Ascending'
|
| 185 |
|
| 186 |
if category_one or category_two or sortby:
|
| 187 |
category_one = category_one_dict[category_one]
|
| 188 |
category_two = category_two_dict[category_two]
|
| 189 |
+
draw('general_reasoning', category_one, category_two, 'Accuracy', sortby, model_size_range)
|
| 190 |
+
|
|
|
|
| 191 |
|
| 192 |
def flores():
|
| 193 |
st.title("Task: FLORES-Translation")
|
|
|
|
| 207 |
'Malay to English': 'zsm2eng'}
|
| 208 |
|
| 209 |
|
| 210 |
+
left, center, middle, _, right = st.columns([0.2, 0.2, 0.2, 0.2 ,0.2])
|
| 211 |
with left:
|
| 212 |
category_one = st.selectbox('Zero or Few Shot', filters_levelone)
|
| 213 |
with center:
|
| 214 |
category_two = st.selectbox('Dataset', filters_leveltwo)
|
| 215 |
+
with middle:
|
| 216 |
+
model_size_range = st.selectbox('Model Size', ['All', '<10B', '10B-30B', '>30B'])
|
| 217 |
|
| 218 |
sortby = 'Ascending'
|
| 219 |
|
| 220 |
if category_one or category_two or sortby:
|
| 221 |
category_one = category_one_dict[category_one]
|
| 222 |
category_two = category_two_dict[category_two]
|
| 223 |
+
draw('flores_translation', category_one, category_two, 'BLEU', sortby, model_size_range)
|
| 224 |
+
|
|
|
|
| 225 |
|
| 226 |
def emotion():
|
| 227 |
st.title("Task: Emotion")
|
|
|
|
| 237 |
category_two_dict = {'Indonesian Emotion Classification': 'ind_emotion',
|
| 238 |
'SST2': 'sst2'}
|
| 239 |
|
| 240 |
+
left, center, middle, _, right = st.columns([0.2, 0.2, 0.2, 0.2 ,0.2])
|
| 241 |
with left:
|
| 242 |
category_one = st.selectbox('Zero or Few Shot', filters_levelone)
|
| 243 |
with center:
|
| 244 |
category_two = st.selectbox('Dataset', filters_leveltwo)
|
| 245 |
+
with middle:
|
| 246 |
+
model_size_range = st.selectbox('Model Size', ['All', '<10B', '10B-30B', '>30B'])
|
| 247 |
+
|
| 248 |
sortby = 'Ascending'
|
| 249 |
|
| 250 |
|
| 251 |
if category_one or category_two or sortby:
|
| 252 |
category_one = category_one_dict[category_one]
|
| 253 |
category_two = category_two_dict[category_two]
|
| 254 |
+
draw('emotion', category_one, category_two, 'Accuracy', sortby, model_size_range)
|
|
|
|
|
|
|
| 255 |
|
| 256 |
def dialogue():
|
| 257 |
st.title("Task: Dialogue")
|
|
|
|
| 269 |
'SAMSum': 'samsum',
|
| 270 |
'DialogSum': 'dialogsum'}
|
| 271 |
|
| 272 |
+
left, center, middle, _, right = st.columns([0.2, 0.2, 0.2, 0.2 ,0.2])
|
| 273 |
with left:
|
| 274 |
category_one = st.selectbox('Zero or Few Shot', filters_levelone)
|
| 275 |
with center:
|
| 276 |
category_two = st.selectbox('Dataset', filters_leveltwo)
|
| 277 |
+
with right:
|
| 278 |
if category_two == 'DREAM':
|
| 279 |
sort = st.selectbox('Sort', ['Accuracy'])
|
| 280 |
else:
|
| 281 |
sort = st.selectbox('Sort', ['Average', 'ROUGE-1', 'ROUGE-2', 'ROUGE-L'])
|
|
|
|
|
|
|
|
|
|
| 282 |
|
| 283 |
+
with middle:
|
| 284 |
+
model_size_range = st.selectbox('Model Size', ['All', '<10B', '10B-30B', '>30B'])
|
| 285 |
+
|
| 286 |
sortby = 'Ascending'
|
| 287 |
|
|
|
|
| 288 |
if category_one or category_two or sort or sortby:
|
| 289 |
category_one = category_one_dict[category_one]
|
| 290 |
category_two = category_two_dict[category_two]
|
| 291 |
+
draw('dialogue', category_one, category_two, sort, sortby, model_size_range)
|
| 292 |
+
|
|
|
|
| 293 |
|
| 294 |
def fundamental_nlp_tasks():
|
| 295 |
st.title("Task: Fundamental NLP Tasks")
|
|
|
|
| 309 |
'RTE': 'rte',
|
| 310 |
'MRPC': 'mrpc'}
|
| 311 |
|
| 312 |
+
left, center, middle, _, right = st.columns([0.2, 0.2, 0.2, 0.2 ,0.2])
|
| 313 |
with left:
|
| 314 |
category_one = st.selectbox('Zero or Few Shot', filters_levelone)
|
| 315 |
with center:
|
| 316 |
category_two = st.selectbox('Dataset', filters_leveltwo)
|
| 317 |
+
with middle:
|
| 318 |
+
model_size_range = st.selectbox('Model Size', ['All', '<10B', '10B-30B', '>30B'])
|
|
|
|
| 319 |
|
| 320 |
sortby = 'Ascending'
|
| 321 |
|
| 322 |
if category_one or category_two or sortby:
|
| 323 |
category_one = category_one_dict[category_one]
|
| 324 |
category_two = category_two_dict[category_two]
|
| 325 |
+
draw('fundamental_nlp_tasks', category_one, category_two, 'Accuracy', sortby, model_size_range)
|
|
|
|
|
|